Artificial Intelligence (cs.AI)

Abstract: Aspect sentiment quad prediction (ASQP) is a challenging yet significant subtask in aspect-based sentiment analysis as it provides a complete aspect-level sentiment structure. However, existing ASQP datasets are usually small and low-density, hindering technical advancement. To expand the capacity, in this paper, we release two new datasets for ASQP, which contain the following characteristics: larger size, more words per sample, and higher density. With such datasets, we unveil the shortcomings of existing strong ASQP baselines and therefore propose a unified one-step solution for ASQP, namely One-ASQP, to detect the aspect categories and to identify the aspect-opinion-sentiment (AOS) triplets simultaneously. Our One-ASQP holds several unique advantages: (1) by separating ASQP into two subtasks and solving them independently and simultaneously, we can avoid error propagation in pipeline-based methods and overcome slow training and inference in generation-based methods; (2) by introducing sentiment-specific horns tagging schema in a token-pair-based two-dimensional matrix, we can exploit deeper interactions between sentiment elements and efficiently decode the AOS triplets; (3) we design ``[NULL]'' token can help us effectively identify the implicit aspects or opinions. Experiments on two benchmark datasets and our released two datasets demonstrate the advantages of our One-ASQP. The two new datasets are publicly released at \url{https://www.github.com/Datastory-CN/ASQP-Datasets}.

Abstract: Deploying NMT models on mobile devices is essential for privacy, low latency, and offline scenarios. For high model capacity, NMT models are rather large. Running these models on devices is challenging with limited storage, memory, computation, and power consumption. Existing work either only focuses on a single metric such as FLOPs or general engine which is not good at auto-regressive decoding. In this paper, we present MobileNMT, a system that can translate in 15MB and 30ms on devices. We propose a series of principles for model compression when combined with quantization. Further, we implement an engine that is friendly to INT8 and decoding. With the co-design of model and engine, compared with the existing system, we speed up 47.0x and save 99.5% of memory with only 11.6% loss of BLEU. The code is publicly available at https://github.com/zjersey/Lightseq-ARM.

Abstract: AI requires heavy amounts of storage and compute with assets that are commonly stored in AI Hubs. AI Hubs have contributed significantly to the democratization of AI. However, existing implementations are associated with certain benefits and limitations that stem from the underlying infrastructure and governance systems with which they are built. These limitations include high costs, lack of monetization and reward, lack of control and difficulty of reproducibility. In the current work, we explore the potential of decentralized technologies - such as Web3 wallets, peer-to-peer marketplaces, storage and compute, and DAOs - to address some of these issues. We suggest that these infrastructural components can be used in combination in the design and construction of decentralized AI Hubs.

Abstract: The Blackboard Architecture provides a mechanism for embodying data, decision making and actuation. Its versatility has been demonstrated across a wide number of application areas. However, it lacks the capability to directly model organizational, spatial and other relationships which may be useful in decision-making, in addition to the propositional logic embodied in the rule-fact-action network. Previous work has proposed the use of container objects and links as a mechanism to simultaneously model these organizational and other relationships, while leaving the operational logic modeled in the rules, facts and actions. While containers facilitate this modeling, their utility is limited by the need to manually define them. For systems which may have multiple instances of a particular type of object and which may build their network autonomously, based on sensing, the reuse of logical structures facilitates operations and reduces storage and processing needs. This paper, thus, presents and assesses two additional concepts to add to the Blackboard Architecture: common properties and generic rules. Common properties are facts associated with containers which are defined as representing the same information across the various objects that they are associated with. Generic rules provide logical propositions that use these generic rules across links and apply to any objects matching their definition. The potential uses of these two new concepts are discussed herein and their impact on system performance is characterized.

Abstract: The Blackboard Architecture provides a mechanism for storing data and logic and using it to make decisions that impact the application environment that the Blackboard Architecture network models. While rule-fact-action networks can represent numerous types of data, the relationships that can be easily modeled are limited by the propositional logic nature of the rule-fact network structure. This paper proposes and evaluates the inclusion of containers and links in the Blackboard Architecture. These objects are designed to allow them to model organizational, physical, spatial and other relationships that cannot be readily or efficiently implemented as Boolean logic rules. Containers group related facts together and can be nested to implement complex relationships. Links interconnect containers that have a relationship that is relevant to their organizational purpose. Both objects, together, facilitate new ways of using the Blackboard Architecture and enable or simply its use for complex tasks that have multiple types of relationships that need to be considered during operations.

Abstract: Despite progress in the field, significant parts of current XAI research are still not on solid conceptual, ethical, or methodological grounds. Unfortunately, these unfounded parts are not on the decline but continue to grow. Many explanation techniques are still proposed without clarifying their purpose. Instead, they are advertised with ever more fancy-looking heatmaps or only seemingly relevant benchmarks. Moreover, explanation techniques are motivated with questionable goals, such as building trust, or rely on strong assumptions about the 'concepts' that deep learning algorithms learn. In this paper, we highlight and discuss these and other misconceptions in current XAI research. We also suggest steps to make XAI a more substantive area of research.

Abstract: To assess the potential applications and limitations of chatbot GPT-3 Davinci-003, this study explored the temporal reliability of personality questionnaires applied to the chatbot and its personality profile. Psychological questionnaires were administered to the chatbot on two separate occasions, followed by a comparison of the responses to human normative data. The findings revealed varying levels of agreement in the chatbot's responses over time, with some scales displaying excellent while others demonstrated poor agreement. Overall, Davinci-003 displayed a socially desirable and pro-social personality profile, particularly in the domain of communion. However, the underlying basis of the chatbot's responses, whether driven by conscious self-reflection or predetermined algorithms, remains uncertain.

Abstract: Semantic communication is expected to be one of the cores of next-generation AI-based communications. One of the possibilities offered by semantic communication is the capability to regenerate, at the destination side, images or videos semantically equivalent to the transmitted ones, without necessarily recovering the transmitted sequence of bits. The current solutions still lack the ability to build complex scenes from the received partial information. Clearly, there is an unmet need to balance the effectiveness of generation methods and the complexity of the transmitted information, possibly taking into account the goal of communication. In this paper, we aim to bridge this gap by proposing a novel generative diffusion-guided framework for semantic communication that leverages the strong abilities of diffusion models in synthesizing multimedia content while preserving semantic features. We reduce bandwidth usage by sending highly-compressed semantic information only. Then, the diffusion model learns to synthesize semantic-consistent scenes through spatially-adaptive normalizations from such denoised semantic information. We prove, through an in-depth assessment of multiple scenarios, that our method outperforms existing solutions in generating high-quality images with preserved semantic information even in cases where the received content is significantly degraded. More specifically, our results show that objects, locations, and depths are still recognizable even in the presence of extremely noisy conditions of the communication channel. The code is available at https://github.com/ispamm/GESCO.

Abstract: This paper introduces a new transformer-based model for the problem of travel time estimation. The key feature of the proposed GCT-TTE architecture is the utilization of different data modalities capturing different properties of an input path. Along with the extensive study regarding the model configuration, we implemented and evaluated a sufficient number of actual baselines for path-aware and path-blind settings. The conducted computational experiments have confirmed the viability of our pipeline, which outperformed state-of-the-art models on both considered datasets. Additionally, GCT-TTE was deployed as a web service accessible for further experiments with user-defined routes.

Abstract: In recent years, there has been an increased focus on early detection, prevention, and prediction of diseases. This, together with advances in sensor technology and the Internet of Things, has led to accelerated efforts in the development of personal health monitoring systems. Semantic technologies have emerged as an effective way to not only deal with the issue of interoperability associated with heterogeneous health sensor data, but also to represent expert health knowledge to support complex reasoning required for decision-making. This study evaluates the state of the art in the use of semantic technologies in sensor-based personal health monitoring systems. Using a systematic approach, a total of 40 systems representing the state of the art in the field are analysed. Through this analysis, six key challenges that such systems must overcome for optimal and effective health monitoring are identified: interoperability, context awareness, situation detection, situation prediction, decision support, and uncertainty handling. The study critically evaluates the extent to which these systems incorporate semantic technologies to deal with these challenges and identifies the prominent architectures, system development and evaluation methodologies that are used. The study provides a comprehensive mapping of the field, identifies inadequacies in the state of the art, and provides recommendations for future research directions.

Abstract: The human brain constantly learns and rapidly adapts to new situations by integrating acquired knowledge and experiences into memory. Developing this capability in machine learning models is considered an important goal of AI research since deep neural networks perform poorly when there is limited data or when they need to adapt quickly to new unseen tasks. Meta-learning models are proposed to facilitate quick learning in low-data regimes by employing absorbed information from the past. Although some models have recently been introduced that reached high-performance levels, they are not biologically plausible. We have proposed a bio-plausible meta-learning model inspired by the hippocampus and the prefrontal cortex using spiking neural networks with a reward-based learning system. Our proposed model includes a memory designed to prevent catastrophic forgetting, a phenomenon that occurs when meta-learning models forget what they have learned as soon as the new task begins. Also, our new model can easily be applied to spike-based neuromorphic devices and enables fast learning in neuromorphic hardware. The final analysis will discuss the implications and predictions of the model for solving few-shot classification tasks. In solving these tasks, our model has demonstrated the ability to compete with the existing state-of-the-art meta-learning techniques.

Abstract: The shapes and morphological features of grains in sand assemblies have far-reaching implications in many engineering applications, such as geotechnical engineering, computer animations, petroleum engineering, and concentrated solar power. Yet, our understanding of the influence of grain geometries on macroscopic response is often only qualitative, due to the limited availability of high-quality 3D grain geometry data. In this paper, we introduce a denoising diffusion algorithm that uses a set of point clouds collected from the surface of individual sand grains to generate grains in the latent space. By employing a point cloud autoencoder, the three-dimensional point cloud structures of sand grains are first encoded into a lower-dimensional latent space. A generative denoising diffusion probabilistic model is trained to produce synthetic sand that maximizes the log-likelihood of the generated samples belonging to the original data distribution measured by a Kullback-Leibler divergence. Numerical experiments suggest that the proposed method is capable of generating realistic grains with morphology, shapes and sizes consistent with the training data inferred from an F50 sand database . We then use a rigid contact dynamic simulator to pour the synthetic sand in a confined volume to form granular assemblies in a static equilibrium state with targeted distribution properties. To ensure third-party validation, 50,000 synthetic sand grains and the 1,542 real synchrotron microcomputed tomography (SMT) scans of the F50 sand, as well as the granular assemblies composed of synthetic sand grains are made available in an open-source repository.

Abstract: In chronic diseases, obtaining a correct diagnosis and providing the most appropriate treatments often is not enough to guarantee an improvement of the clinical condition of a patient. Poor adherence to medical prescriptions constitutes one of the main causes preventing achievement of therapeutic goals. This is generally true especially for certain diseases and specific target patients, such as children. An engaging and entertaining technology can be exploited in support of clinical practices to achieve better health outcomes. Our assumption is that a gamified session with a humanoid robot, compared to the usual methodologies for therapeutic education, can be more incisive in learning the correct inhalation procedure in children affected by asthma. In this perspective, we describe an interactive module implemented on the Pepper robotic platform and the setting of a study that was planned in 2020 to be held at the Pneumoallergology Pediatric clinic of CNR in Palermo. The study was canceled due to the pandemic and the subsequent and permanent closure of the clinic. Our long-term goal is to assess, by means of a qualitative-quantitative survey plan, the impact of such an educational action, evaluating possible improvement in the adherence to the treatment.

Abstract: Planning is a data efficient decision-making strategy where an agent selects candidate actions by exploring possible future states. To simulate future states when there is a high-dimensional action space, the knowledge of one's decision making strategy must be used to limit the number of actions to be explored. We refer to the model used to simulate one's decisions as the agent's self-model. While self-models are implicitly used widely in conjunction with world models to plan actions, it remains unclear how self-models should be designed. Inspired by current reinforcement learning approaches and neuroscience, we explore the benefits and limitations of using a distilled policy network as the self-model. In such dual-policy agents, a model-free policy and a distilled policy are used for model-free actions and planned actions, respectively. Our results on a ecologically relevant, parametric environment indicate that distilled policy network for self-model stabilizes training, has faster inference than using model-free policy, promotes better exploration, and could learn a comprehensive understanding of its own behaviors, at the cost of distilling a new network apart from the model-free policy.

Abstract: The increasing prevalence of image-altering filters on social media and video conferencing technologies has raised concerns about the ethical and psychological implications of using Artificial Intelligence (AI) to manipulate our perception of others. In this study, we specifically investigate the potential impact of blur filters, a type of appearance-altering technology, on individuals' behavior towards others. Our findings consistently demonstrate a significant increase in selfish behavior directed towards individuals whose appearance is blurred, suggesting that blur filters can facilitate moral disengagement through depersonalization. These results emphasize the need for broader ethical discussions surrounding AI technologies that modify our perception of others, including issues of transparency, consent, and the awareness of being subject to appearance manipulation by others. We also emphasize the importance of anticipatory experiments in informing the development of responsible guidelines and policies prior to the widespread adoption of such technologies.

Abstract: One of the greatest challenges facing our society is the discovery of new innovative crystal materials with specific properties. Recently, the problem of generating crystal materials has received increasing attention, however, it remains unclear to what extent, or in what way, we can develop generative models that consider both the periodicity and equivalence geometric of crystal structures. To alleviate this issue, we propose two unified models that act at the same time on crystal lattice and atomic positions using periodic equivariant architectures. Our models are capable to learn any arbitrary crystal lattice deformation by lowering the total energy to reach thermodynamic stability. Code and data are available at https://github.com/aklipf/GemsNet.

Abstract: The increasing reliance on Large Language Models (LLMs) across academia and industry necessitates a comprehensive understanding of their robustness to prompts. In response to this vital need, we introduce PromptBench, a robustness benchmark designed to measure LLMs' resilience to adversarial prompts. This study uses a plethora of adversarial textual attacks targeting prompts across multiple levels: character, word, sentence, and semantic. These prompts are then employed in diverse tasks, such as sentiment analysis, natural language inference, reading comprehension, machine translation, and math problem-solving. Our study generates 4,032 adversarial prompts, meticulously evaluated over 8 tasks and 13 datasets, with 567,084 test samples in total. Our findings demonstrate that contemporary LLMs are vulnerable to adversarial prompts. Furthermore, we present comprehensive analysis to understand the mystery behind prompt robustness and its transferability. We then offer insightful robustness analysis and pragmatic recommendations for prompt composition, beneficial to both researchers and everyday users. We make our code, prompts, and methodologies to generate adversarial prompts publicly accessible, thereby enabling and encouraging collaborative exploration in this pivotal field: https://github.com/microsoft/promptbench.

Abstract: Propositional model counting (#SAT) can be solved efficiently when the input formula is in deterministic decomposable negation normal form (d-DNNF). Translating an arbitrary formula into a representation that allows inference tasks, such as counting, to be performed efficiently, is called knowledge compilation. Top-down knowledge compilation is a state-of-the-art technique for solving #SAT problems that leverages the traces of exhaustive DPLL search to obtain d-DNNF representations. While knowledge compilation is well studied for propositional approaches, knowledge compilation for the (quantifier free) counting modulo theory setting (#SMT) has been studied to a much lesser degree. In this paper, we discuss compilation strategies for #SMT. We specifically advocate for a top-down compiler based on the traces of exhaustive DPLL(T) search.

Abstract: Circumscription is one of the main approaches for defining non-monotonic description logics (DLs). While the decidability and complexity of traditional reasoning tasks such as satisfiability of circumscribed DL knowledge bases (KBs) is well understood, for evaluating conjunctive queries (CQs) and unions thereof (UCQs), not even decidability had been established. In this paper, we prove decidability of (U)CQ evaluation on circumscribed DL KBs and obtain a rather complete picture of both the combined complexity and the data complexity, for DLs ranging from ALCHIO via EL to various versions of DL-Lite. We also study the much simpler atomic queries (AQs).

Abstract: Humor is a central aspect of human communication that has not been solved for artificial agents so far. Large language models (LLMs) are increasingly able to capture implicit and contextual information. Especially, OpenAI's ChatGPT recently gained immense public attention. The GPT3-based model almost seems to communicate on a human level and can even tell jokes. Humor is an essential component of human communication. But is ChatGPT really funny? We put ChatGPT's sense of humor to the test. In a series of exploratory experiments around jokes, i.e., generation, explanation, and detection, we seek to understand ChatGPT's capability to grasp and reproduce human humor. Since the model itself is not accessible, we applied prompt-based experiments. Our empirical evidence indicates that jokes are not hard-coded but mostly also not newly generated by the model. Over 90% of 1008 generated jokes were the same 25 Jokes. The system accurately explains valid jokes but also comes up with fictional explanations for invalid jokes. Joke-typical characteristics can mislead ChatGPT in the classification of jokes. ChatGPT has not solved computational humor yet but it can be a big leap toward "funny" machines.